© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88750
    Prev
    Next
    INDEX
    Explanations

    positive and negative qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Budd
    -0.12
     kla
    -0.12
     Sachs
    -0.12
     davon
    -0.12
     PEOPLE
    -0.12
     erfolgre
    -0.11
    341
    -0.11
    .defaults
    -0.11
     Tat
    -0.11
    ennen
    -0.11
    POSITIVE LOGITS
     somehow
    0.09
     enough
    0.09
     sounding
    0.08
     enticing
    0.08
     tempting
    0.08
     deterrent
    0.07
     to
    0.07
     arous
    0.07
     taken
    0.07
     me
    0.07
    Activations Density 0.094%

    No Known Activations